Through extensive experiments on two mathematical reasoning benchmarks, namely GSM8k and MATH, we reveal the extraordinary capabilities of our model.
Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+.
Ranked #15 on Code Generation on HumanEval
In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans.
First, it is the largest multi-modal conversation dataset by the number of dialogues by 88x.
Ranked #2 on Multimodal Intent Recognition on MMDialog
(2) How to cohere with context and preserve the knowledge when generating a stylized response.
This paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks.
In such a low-resource setting, we devise a novel conversational agent, Divter, in order to isolate parameters that depend on multimodal dialogues from the entire generation model.
Most of the current effective methods for text classification tasks are based on large-scale labeled data and a great number of parameters, but when the supervised training data are few and difficult to be collected, these models are not available.